© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 97620
    Prev
    Next
    INDEX
    Explanations

    brain anatomy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vectorielle
    -1.11
     germs
    -1.06
     abstrait
    -0.96
     auroit
    -0.96
     RIPRODUZIONE
    -0.94
     réaliste
    -0.94
     normaux
    -0.93
     Shakspeare
    -0.92
     vectorielles
    -0.91
     feroit
    -0.91
    POSITIVE LOGITS
    er
    0.57
    oles
    0.53
     ‘
    0.52
     '
    0.52
     “
    0.52
     "
    0.52
     er
    0.51
    ling
    0.50
     il
    0.50
     per
    0.49
    Activations Density 0.097%

    No Known Activations